Ruprecht-Karls-Universitšt Heidelberg

Image Analysis

Image analysis is the science and art of extracting quantitative measurements from, or detecting and recognizing objects in, images. Given that imaging sensors are starting to be built into every phone, car, and other appliances, this is a burgeoning field. Its methods also allow to ask and answer new questions in data-intensive sciences such as large-scale astronomical sky surveys, or in neurobiology.

This lecture will give you insight into ideas, mathematical and algorithmic techniques ranging from low-level concepts such as unitary transforms all the way to highly engineered feature descriptors that are at the heart of modern object recognition pipelines.

This lecture assumes no prior experience in pattern recognition or image analysis.


Example application of image analysis.
High resolution electron microscopy volume images of brain tissue are acquired in the hope of being able to reconstruct the wiring of the neurons in the brain. With data sizes up to multiple terabytes, automated analysis is required. On the right, the watershed transform is used to segment the image into many different segments. A subsequent optimization step improves the segmentation result, such that (ideally), each neuron corresponds to a single segment.

Data: W. Denk, K. Briggman, MPI for Medical Research, Heidelberg.

Lecture Videos (Youtube playlist)

General information

  • Lecturer: Prof. Dr. Fred Hamprecht
  • TA: Christoph Decker
  • Lecture: Tuesday, 14.15-16.00, Wednesday, 14.15-16.00
    HCI, Speyerer Strasse 6, large seminar room
  • Exercises: Wednesday, 16.15-18.00 (same place as lecture)

Additional Material

Recommended Literature

  • S. J. D. Prince: Computer Vision: Models, Learning, and Inference. Cambridge Univ. Press, 2012
  • M. Sonka, V. Hlavac, R. Boyle: Image Processing, Analysis and Machine Vision.
    Thomson Learning, 2008.
  • B. Jähne: Digital Image Processing.
    Springer, 2012.
Last update: 24.04.2015, 12:33
zum Seitenanfang